FakeCrawler.go

package main

import (
    "fmt"
)

type Fetcher interface {
    // Fetch returns the body of URL and
    // a slice of URLs found on that page.
    Fetch(url string) (body string, urls []string, err error)
}

type CrawlInfo struct {
    Body string 
  Urls []string
    Depth int
}

func DoCrawl(url string, depth int, fetcher Fetcher,
            ch chan *CrawlInfo, quit chan int) {
    if depth <= 0 {
        quit <- 0
        return
    }
    
    body, urls, err := fetcher.Fetch(url)
    if err != nil {
        fmt.Println(err)
        quit <- 0
    } else {
        ch <- &CrawlInfo{body, urls, depth}
        quit <- 0
    }
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher) {
    // TODO: Fetch URLs in parallel.
    // TODO: Don't fetch the same URL twice.
    // This implementation doesn't do either:
    if depth <= 0 {
        return
    }
    ch := make(chan *CrawlInfo)
    quit := make(chan int)
    m := make(map[string]*CrawlInfo)
    noRoutines := 1
    
    go DoCrawl(url, depth, fetcher, ch, quit)
    
    for noRoutines > 0 {
        select {
        case <- quit:
            noRoutines--
            fmt.Println(noRoutines)
        case cinfo := <- ch:
            dep := cinfo.Depth
            for _, url := range(cinfo.Urls) {
                _, ok := m[url]
                if ok == false {
                  m[url] = cinfo
                  noRoutines++
                  fmt.Println(noRoutines, m)
                  go DoCrawl(url, dep - 1, fetcher,
                           ch, quit)
                }
            }
        }
    }
    
    for k, v:= range(m) {
    	fmt.Println(k, v.Body)
    }
    
    return
}

func main() {
    Crawl("http://golang.org/", 4, fetcher)
}

// fakeFetcher is Fetcher that returns canned results.
type fakeFetcher map[string]*fakeResult

type fakeResult struct {
    body string
    urls []string
}

func (f *fakeFetcher) Fetch(url string) (string, []string, error) {
    if res, ok := (*f)[url]; ok {
        return res.body, res.urls, nil
    }
    return "", nil, fmt.Errorf("not found: %s", url)
}

// fetcher is a populated fakeFetcher.
var fetcher = &fakeFetcher{
    "http://golang.org/": &fakeResult{
        "The Go Programming Language",
        []string{
            "http://golang.org/pkg/",
            "http://golang.org/cmd/",
        },
    },
    "http://golang.org/pkg/": &fakeResult{
        "Packages",
        []string{
            "http://golang.org/",
            "http://golang.org/cmd/",
            "http://golang.org/pkg/fmt/",
            "http://golang.org/pkg/os/",
        },
    },
    "http://golang.org/pkg/fmt/": &fakeResult{
        "Package fmt",
        []string{
            "http://golang.org/",
            "http://golang.org/pkg/",
        },
    },
    "http://golang.org/pkg/os/": &fakeResult{
        "Package os",
        []string{
            "http://golang.org/",
            "http://golang.org/pkg/",
        },
    },
}